Maybe. with current xeon's I have not seen this. I believe at one point some one else from the foundry said something about hyperthreading and Nuke but that was a few versions ago. But I know in a test I did today after getting this setting the threads from 8 to 16 cause a slow down. the sweet spot was 12 but the script I was using was including a 3d scene was small, around a hundred or so nodes. At 16 it pegged the cpus and it was slower then 8. At 12 I got a substantial increase over 8 (more then it seems it should have been) We need that shake script test boat thing for nuke.
Randy S. Little http://www.rslittle.com <http://reel.rslittle.com> On Tue, Jan 24, 2012 at 23:00, Peter Pearson <[email protected]> wrote: > On 25/01/12 02:31, Randy Little wrote: > >> The only reason it wouldn't be is that its already being set in a launch >> script. Hyper threading Nuke to MAX virtual cores is not so fast. I >> some times get better results when setting to max real threads or >> leaving at least 4 threads for i/o. >> > > It depends on the workload, but the hyperthreading of the Intel Core i7s > is much better than the old Pentium 4 hyperthreading (which caused a lot of > stuff to slow down), so you should see close to a doubling of performance > for most stuff... > > Peter > -- > Peter Pearson, Software Engineer > The Foundry, 6th Floor, The Communications Building, > 48 Leicester Square, London, UK, WC2H 7LT > Tel: +44 (0)20 7434 0449 Web: www.thefoundry.co.uk > > The Foundry Visionmongers Ltd. > Registered in England and Wales No: 4642027 > > ______________________________**_________________ > Nuke-users mailing list > [email protected].**co.uk<[email protected]>, > http://forums.thefoundry.co.**uk/ <http://forums.thefoundry.co.uk/> > http://support.thefoundry.co.**uk/cgi-bin/mailman/listinfo/**nuke-users<http://support.thefoundry.co.uk/cgi-bin/mailman/listinfo/nuke-users> >
_______________________________________________ Nuke-users mailing list [email protected], http://forums.thefoundry.co.uk/ http://support.thefoundry.co.uk/cgi-bin/mailman/listinfo/nuke-users
